U
    >vf7                     @   s  d dl Z d dlmZ d dlZd dlZd dlmZ d dlZd dlZ	d dl
Z
d dlmZ d dlm  mZ d dlZd dlmZ e
jdd Ze
jdeddfd	dgfgd
dd ZG dd dZdd Zdd Zdd Zdd Zdd Zdd Z e
j!"dddgdd Z#d d! Z$d"d# Z%d$d% Z&d&d' Z'd(d) Z(d*d+ Z)d,d- Z*d.d/ Z+d0d1 Z,d2d3 Z-e
j!"d4d5d6d7gd8d9 Z.d:d; Z/d<d= Z0dS )>    N)datetime)Path)EmptyDataErrorc                 C   s   | dddS )Niosasdata )datapathr   r   E/tmp/pip-unpacked-wheel-vdrwu74i/pandas/tests/io/sas/test_sas7bdat.pydirpath   s    r            )paramsc                 C   s   | j \}}tj|d| d}t|}tddd}tj|d dd}|| |d< tj|d dd}|| |d< t|j	d D ]D}	|j
d d |	f }
|
jtjkr||	|j
d d |	f tj q||fS )	NZtest_sas7bdat_z.csvi  r   ZColumn4d)unitZColumn12)paramospathjoinpdread_csvr   Zto_timedeltarangeshapeilocdtypenpZint64Zisetitemastypefloat64)requestr   itest_ixfnamedfepocht1t2kcolr   r   r
   data_test_ix   s    

$r)   c                   @   s   e Zd Zejjdd Zejjdd Zejjdd Zejjdd Z	e
d	ejjd
d Zejjejddejdedddd Zdd ZdS )TestSAS7BDATc                 C   sF   |\}}|D ]4}t j|d| d}tj|dd}t|| qd S Ntest	.sas7bdatutf-8encoding)r   r   r   r   read_sastmassert_frame_equalselfr   r)   df0r!   r'   r"   r#   r   r   r
   test_from_file*   s
    zTestSAS7BDAT.test_from_filec              
   C   s   |\}}|D ]x}t j|d| d}t|d}| }W 5 Q R X t|}	tj|	dddd}
|
 }W 5 Q R X t	j
||dd	 qd S )
Nr,   r-   rbsas7bdatTr.   formatiteratorr0   FZcheck_exact)r   r   r   openreadr   BytesIOr   r1   r2   r3   )r5   r   r)   r6   r!   r'   r"   fZbytsbufrdrr#   r   r   r
   test_from_buffer2   s    
   zTestSAS7BDAT.test_from_bufferc           	   
   C   s   |\}}|D ]}t j|d| d}tj|dddV}|d}t||jddd d f  |d}t||jdd	d d f  W 5 Q R X qd S )
Nr,   r-   Tr.   r<   r0   r   r         )	r   r   r   r   r1   r?   r2   r3   r   )	r5   r   r)   r6   r!   r'   r"   rC   r#   r   r   r
   test_from_iterator@   s    

zTestSAS7BDAT.test_from_iteratorc                 C   sJ   |\}}|D ]8}t tj|d| d}tj|dd}t|| qd S r+   )r   r   r   r   r   r1   r2   r3   r4   r   r   r
   test_path_pathlibK   s
    zTestSAS7BDAT.test_path_pathlibzpy.pathc           	      C   sV   ddl m} |\}}|D ]8}|tj|d| d}tj|dd}t|| qd S )Nr   )localr,   r-   r.   r/   )	Zpy.pathrJ   r   r   r   r   r1   r2   r3   )	r5   r   r)   Z	LocalPathr6   r!   r'   r"   r#   r   r   r
   test_path_localpathS   s    z TestSAS7BDAT.test_path_localpath	chunksize)rF   rG   
      r'   r      c              	   C   s`   t j|d| d}tj||dd"}d}|D ]}||jd 7 }q0W 5 Q R X ||jks\td S )Nr,   r-   r.   )rL   r0   r   )r   r   r   r   r1   r   	row_countAssertionError)r5   r   r'   rL   r"   rC   yxr   r   r
   test_iterator_loop^   s    zTestSAS7BDAT.test_iterator_loopc              	   C   sx   t j|d}tj|dddd}||jd }W 5 Q R X tj|ddd}||jd }W 5 Q R X t|| d S )Ntest1.sas7bdatr9   Tr.   r:      rE   )	r   r   r   r   r1   r?   rP   r2   r3   )r5   r   r"   rC   d1Zd2r   r   r
   test_iterator_read_too_muchj   s       z(TestSAS7BDAT.test_iterator_read_too_muchN)__name__
__module____qualname__pytestmarkZslowr7   rD   rH   rI   tdZ
skip_if_norK   parametrizer   rT   rX   r   r   r   r
   r*   )   s    




		r*   c           
   	   C   s   | dddd}t |}t j|dd}|jD ]2}z|| jd||< W q, tk
r\   Y q,X q,t|| ddlm	} t
||d	d
}| }W 5 Q R X t|j|jD ]\}}	||	 kstqd S )Nr   r   r   rU   r.   r/   r   )SAS7BDATReaderF)Zconvert_header_text)r   r1   columnsstrdecodeAttributeErrorr2   r3   Zpandas.io.sas.sas7bdatr`   
contextlibclosingr?   ziprQ   )
r	   r"   df1df2r(   r`   rC   Zdf3rS   rR   r   r   r
   test_encoding_optionsw   s    

rj   c              	   C   st   | dddd}t j|ddd}|jdks.t| }W 5 Q R X t j|ddd}| }W 5 Q R X t|| d S )	Nr   r   r   rU   ZinferT)r0   r<   cp1252)r   r1   Zinferred_encodingrQ   r?   r2   r3   )r	   r"   Z
df1_readerrh   Z
df2_readerri   r   r   r
   test_encoding_infer   s    rl   c                 C   sj   | dddd}t j|dd}| dddd}t j|dgd	}d
dddg}|| tj||< t|| d S )Nr   r   r   zproductsales.sas7bdatr.   r/   zproductsales.csvZMONTHZparse_datesZACTUALZPREDICTZQUARTERZYEARr   r1   r   r   r   r   r2   r3   )r	   r"   r#   r6   Zvnr   r   r
   test_productsales   s    ro   c                 C   sL   | dddd}t |}| dddd}t |}|tj}t|| d S )Nr   r   r   ztest_12659.sas7bdatztest_12659.csvrn   r	   r"   r#   r6   r   r   r
   
test_12659   s    

rq   c                 C   sP   | dddd}t |}| dddd}t |}|tj}tj||dd d S )Nr   r   r   zairline.sas7bdatzairline.csvFr=   rn   rp   r   r   r
   test_airline   s    

rr   c                 C   sr   | dddd}t |}| dddd}t j|dddd	d
gd}|jd d df jd||jd < t|| d S )Nr   r   r   zdatetime.sas7bdatzdatetime.csvZDate1ZDate2DateTimeZ
DateTimeHiZTaiwrm   rF   us)	r   r1   r   r   dtroundra   r2   r3   rp   r   r   r
   test_date_time   s    
 $rw   columnZWGTZCYLc                 C   sD   | dddd}t j|dd}|| }||  }tj||dd d S )	Nr   r   r   zcars.sas7bdatlatin-1r/   Tr=   )r   r1   rv   r2   Zassert_series_equal)r	   rx   r"   r#   resultexpectedr   r   r
   test_compact_numerical_values   s
    r|   c                 C   sH   | dddd}t j|dd}| dddd}t j|dd}t|| d S )Nr   r   r   zmany_columns.sas7bdatry   r/   zmany_columns.csvr   r1   r   r2   r3   rp   r   r   r
   test_many_columns   s
    r~   c                 C   s0   | dddd}t j|dd}t|dks,td S )Nr   r   r   zload_log.sas7bdatry   r/   i1  r   r1   lenrQ   r	   r"   r#   r   r   r
    test_inconsistent_number_of_rows   s    r   c              	   C   s6   | dddd}t jtdd t| W 5 Q R X d S )Nr   r   r   zzero_variables.sas7bdatzNo columns to parse from filematch)r\   raisesr   r   r1   )r	   r"   r   r   r
   test_zero_variables   s    r   c                 C   sD   | dddd}t |}t dddgjd d }t|| d S )	Nr   r   r   zzero_rows.sas7bdatag      ?)Z
char_fieldZ	num_fieldr   )r   r1   	DataFramer   r2   r3   )r	   r"   rz   r{   r   r   r
   test_zero_rows   s    
r   c              	   C   s:   | dddd}d}t jt|d t| W 5 Q R X d S )Nr   r   r   zcorrupt.sas7bdatz4'SAS7BDATReader' object has no attribute 'row_count'r   )r\   r   rd   r   r1   )r	   r"   msgr   r   r
   test_corrupt_read   s    r   c                 C   sj   t | tr*| jtt| jdd d dS t | trbtjj	| d}|jtt|jdd d dS | S d S )N  )microsecond)Ztimestr)

isinstancer   replaceintrv   r   rb   dateutilparserparse)ts_tsr   r   r
   round_datetime_to_ms   s    
 
 r   c                 C   s  | dddd}t j|dd}|dd }z|d	 jd
|d	< W nJ t jjjjk
rh   |t	}Y n& t
k
r   |d	 t	|d	< Y nX t jddgddgtdddddddtdddddddgddgtdddtdddgdddd	ddgd}t|| d S ) Nr   r   r   max_sas_date.sas7bdat
iso-8859-1r/   c                 S   s   t | tr|  S | S Nr   rb   lstriprS   r   r   r
   <lambda>      z#test_max_sas_date.<locals>.<lambda>dt_as_dtrt   maxnormal`MBA'           ;   X> i     r      qgFA    @@textdt_as_floatr   date_as_floatdate_as_dater   r   r   r   ra   )r   r1   applymapru   rv   _libstslibsnp_datetimeOutOfBoundsDatetimer   rd   applyr   r   r2   r3   r	   r"   r#   r{   r   r   r
   test_max_sas_date  s*    
r   c                 C   sR  dddddg}| dddd	}g }t j|d
ddD ]}|dd }z|d jd|d< W nJ t jjjjk
r   |t	}Y n& t
k
r   |d t	|d< Y nX |jddd || q0t jdgdgtdddddddgdgtdddgd|dt jdgdgtdgd gtd!gd|dg}t||D ]\}}t|| q6d S )"Nr   r   r   r   r   r   r   r   r   r   r   )r0   rL   c                 S   s   t | tr|  S | S r   r   r   r   r   r
   r   1  r   z,test_max_sas_date_iterator.<locals>.<lambda>rt   T)ZinplaceZdropr   r   r   r   r   r   r   r   r   r   r   r   r   z2019-08-01 23:59:59.999r   z
2019-08-01)r   r1   r   ru   rv   r   r   r   r   r   rd   r   Zreset_indexappendr   r   r   Z
datetime64rg   r2   r3   )r	   Z	col_orderr"   resultsr#   r{   rz   r   r   r
   test_max_sas_date_iterator'  sD    


r   c                 C   s`   | dddd}t j|dd}t tddd	t jgtddd	d
dddt jgd}t|| d S )Nr   r   r   zdates_null.sas7bdatr.   r/   r   r   r   r   r   iQ> )ZdatecolZdatetimecol)r   r1   r   r   ZNaTr2   r3   r   r   r   r
   test_null_dateU  s    
r   c                 C   s,   | dddd}t |}t|dks(td S )Nr   r   r   ztest_meta2_page.sas7bdatr   r   r   r   r   r
   test_meta2_pageh  s    
r   z8test_file, override_offset, override_value, expected_msg)test2.sas7bdat    Out of bounds)r   r   r   zunknown control byte)ztest3.sas7bdati    r   c              	   C   sf   t | ddd|d}t| }W 5 Q R X |||< tjt|d tjt	|dd W 5 Q R X dS )	z1Errors in RLE/RDC decompression should propagate.r   r   r   r8   r   r9   )r;   N)
r>   	bytearrayr?   r\   r   	Exceptionr   r1   r   r@   )r	   Z	test_fileZoverride_offsetZoverride_valueZexpected_msgfdr   r   r   r
   test_rle_rdc_exceptionso  s
    r   c                 C   sH   | dddd}t j|dd}| dddd}t j|dd	}t|| d S )
Nr   r   r   z0x40controlbyte.sas7bdatasciir/   z0x40controlbyte.csvobject)r   r}   rp   r   r   r
   test_0x40_control_byte  s
    r   c                 C   s2   | dddd}t tj|dd}|jdks.td S )Nr   r   r   z0x00controlbyte.sas7bdat.bz2*  )rL   )r   rV   )nextr   r1   r   rQ   r   r   r   r
   test_0x00_control_byte  s    r   )1re   r   r   r   pathlibr   Zdateutil.parserr   Znumpyr   r\   Zpandas.errorsr   Zpandas.util._test_decoratorsutilZ_test_decoratorsr^   Zpandasr   Zpandas._testingZ_testingr2   Zfixturer   r   r)   r*   rj   rl   ro   rq   rr   rw   r]   r_   r|   r~   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r
   <module>   sX   

N
		
	
#.
	